Realizing the Costs: Template-Based Surface Realisation in the GRAPH Approach to Referring Expression Generation
نویسندگان
چکیده
We describe a new realiser developed for the TUNA 2009 Challenge, and present its evaluation scores on the development set, showing a clear increase in performance compared to last year’s simple realiser.
منابع مشابه
Template-Based Surface Realization for Referring Expression Generation
This paper describes the template-based surface realizer which was used by the GRAPH team in the TUNA-REG Challenge 2009 in combination with an attribute selection algorithm used in previous editions of the TUNA challenges. The new template-based realizer is compared to the realizer used by the GRAPH team in the REG 2008 Challenge and to an improved version of the 2008 realizer. Results show no...
متن کاملGRAPH: The Costs of Redundancy in Referring Expressions
We describe a graph-based generation system that participated in the TUNA attribute selection and realisation task of the REG 2008 Challenge. Using a stochastic cost function (with certain properties for free), and trying attributes from cheapest to more expensive, the system achieves overall .76 DICE and .54 MASI scores for attribute selection on the development set. For realisation, it turns ...
متن کاملStatistical Surface Realisation of Portuguese Referring Expressions
Natural Language Generation systems usually require substantial knowledge about the structure of the target language in order to perform the final task in the generation process – the mapping from semantic representation to text known as surface realisation. Designing knowledge bases of this kind, typically represented as sets of grammar rules, may however become a costly, labour-intensive ente...
متن کاملText Polishing: Surface-Oriented Smoothing of Generated Text via Markup-Based Revision Rules
In this paper, we introduce text polishing, a novel, surface-oriented approach to using revisions in natural language generation in order to improve the fluency of generated texts. In this approach, markupbased revision rules are used to implement sentence planning operations such as aggregation, referring expression generation and discourse marker insertion. By working close to the surface, we...
متن کاملHierarchical Reinforcement Learning for Adaptive Text Generation
We present a novel approach to natural language generation (NLG) that applies hierarchical reinforcement learning to text generation in the wayfinding domain. Our approach aims to optimise the integration of NLG tasks that are inherently different in nature, such as decisions of content selection, text structure, user modelling, referring expression generation (REG), and surface realisation. It...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2009